© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40686
    Prev
    Next
    INDEX
    Explanations

    but, and,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    гоÑĢа
    -0.08
    æģ©çĪ±
    -0.07
    çŃīæľīåħ³
    -0.07
    itorium
    -0.07
    vla
    -0.07
    abra
    -0.07
    اء
    -0.07
    æ¶īåıĬçīĪæĿĥ
    -0.07
    大åħ¨
    -0.07
    说çļĦæĺ¯
    -0.07
    POSITIVE LOGITS
    çľĭåĪ°è¿Ļ个
    0.08
    éĢļè¿ĩè¿Ļ个
    0.07
    èĢĮè¿Ļ个
    0.07
    让è¿Ļ个
    0.07
    è¿Ļä¸Ģ次çļĦ
    0.07
    è¿Ļ次
    0.07
    çijľ
    0.07
    elum
    0.07
    omb
    0.06
    acher
    0.06
    Activations Density 0.206%

    No Known Activations